align

# /align - Force N numbered clarifying questions before doing any work Manual escalation lever above the default `prompt-refinement.md` rule. When the user invokes `/align N` they are explicitly summoning a clarification gate with exactly N numbered + lettered questions, each carrying a single committed recommendation. Single-shot per invocation - after Phase 3 approval the skill exits and normal posture resumes. Design spec: `docs/superpowers/specs/2026-05-13-align-skill-design.md` (data overlay: `.heading-os-data/docs/superpowers/specs/2026-05-13-align-skill-design.md`). ## Phase 1 - Pre-flight + target identification Three sub-steps, all silent on success. ### 1.1 Parse and validate N Read `$ARGUMENTS`: - Empty -> `N = 5` (default) - Integer string `"1"` through `"10"` -> `N = int(arg)` - Anything else (`"0"`, `"100"`, `"abc"`, `"5.5"`, `"-3"`) -> abort with the single-line error and stop. The error is the entire output: ``` /align expects N between 1 and 10. Got: {arg}. Try `/align 5`. ``` ### 1.2 Detect CEO vs exec context One Glob call to set the recommendation label: ``` Glob("reference/misha-voice.md") ``` - Match found -> `voice_mode = "ceo"`, label = `Моя рекомендация`. Bilingual EN/RU per the user's preceding message language. - No match -> `voice_mode = "exec"`, label = `My recommendation`. English-only. The voice_mode flag controls only the label string, not the conversation language. Conversation language always matches the user's last mess...